Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3554 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6972. Min Act: -0.0001

Data Index: 467151 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5823. Min Act: -0.0000

Data Index: 12601 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6007. Min Act: -0.0000

Data Index: 940513 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5742. Min Act: -0.0001

Data Index: 274777 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5543. Min Act: -0.0001

Data Index: 131181 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5928. Min Act: -0.0001

Data Index: 762319 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5543. Min Act: -0.0000

Data Index: 237748 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1209447 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5413. Min Act: -0.0000

Data Index: 547948 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5092. Min Act: -0.0000

Data Index: 396559 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5008. Min Act: -0.0000

Data Index: 679050 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1032657 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5112. Min Act: -0.0001

Data Index: 1115539 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4470. Min Act: -0.0001

Data Index: 653845 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4772. Min Act: -0.0000

Data Index: 862366 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5260. Min Act: -0.0001

Data Index: 288482 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4748. Min Act: -0.0001

Data Index: 53065 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4724. Min Act: -0.0000

Data Index: 819308 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4569. Min Act: -0.0000

Data Index: 73823 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4839. Min Act: -0.0000

Data Index: 982474 (C4 (Web Text))

Max Activating Token Index: 260